© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32043
    Prev
    Next
    INDEX
    Explanations

    common phrases and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite

    can, just, without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cc
    0.42
     actor
    0.41
     extensively
    0.41
    pinned
    0.39
    Statuses
    0.39
     capped
    0.39
     alcoholism
    0.39
     니
    0.39
     silent
    0.38
     LC
    0.38
    POSITIVE LOGITS
     epoca
    0.54
    Очень
    0.51
    ंबकीय
    0.50
    消費者
    0.50
    時刻
    0.50
    ସ
    0.49
    ochi
    0.47
    чора
    0.47
    कृपया
    0.47
    សូម
    0.46
    Activations Density 0.000%

    No Known Activations